Related papers: ZeroED: Hybrid Zero-shot Error Detection through L…

Medical image segmentation has achieved remarkable success through the continuous advancement of UNet-based and Transformer-based foundation backbones. However, clinical diagnosis in the real world often requires integrating domain…

The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially…

Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful…

Recent advancements in Document Layout Analysis through Large Language Models and Multimodal Models have significantly improved layout detection. However, despite these improvements, challenges remain in addressing critical structural…

Using a taxonomy to organize information requires classifying objects (documents, images, etc) with appropriate taxonomic classes. The flexible nature of zero-shot learning is appealing for this task because it allows classifiers to…

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of…

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…

Deep learning increasingly relies on massive data with substantial storage, annotation, and training costs. To reduce costs, coreset selection finds a representative subset of data to train models while ideally performing on par with the…

Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods…

The inherent complexity of structured longitudinal Electronic Health Records (EHR) data poses a significant challenge when integrated with Large Language Models (LLMs), which are traditionally tailored for natural language processing.…

Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple…

Recent advancements in large language models (LLMs) demonstrate exceptional Chinese text processing capabilities, particularly in Chinese Spelling Correction (CSC). While LLMs outperform traditional BERT-based models in accuracy and…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Zero-shot learning (ZL) is crucial for tasks involving unseen categories, such as natural language processing, image classification, and cross-lingual transfer.Current applications often fail to accurately infer and handle new relations…

High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or…

Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Controllers for structured LM reasoning (e.g., Chain-of-Thought, self-consistency, and Tree-of-Thoughts) often entangle what to try next with how to execute it, exposing only coarse global knobs and yielding brittle, compute-inefficient,…

Event detection (ED), aiming to detect events from texts and categorize them, is vital to understanding actual happenings in real life. However, mainstream event detection models require high-quality expert human annotations of triggers,…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…